Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    playfully mischievous or creative explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marco
    0.43
    动的
    0.43
    _
    0.41
     -
    0.41
     عندهم
    0.40
    ô
    0.40
     receive
    0.40
     Cube
    0.40
     of
    0.39
     भर
    0.39
    POSITIVE LOGITS
    AndroidResource
    0.51
     файла
    0.47
    }}\
    0.45
     amélior
    0.44
     fogy
    0.44
     interno
    0.44
     εργ
    0.44
    鸠
    0.44
    対策
    0.44
    ější
    0.44
    Act Density 0.002%

    No Known Activations